Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 4 of 4 for “"Policy-improvement algorithm"”.

  1. Almost Sure Safety and Continual Improvement in Reinforcement Learning

    … from optimality, and characterize the feasible policy sets in three settings, depending on the structure of the state and action spaces. For two of these regimes, we establish finite-sample guarantees to learn these sets with high probability. For the remaining one, we characterize almost-sure …

    jhu Repository record for Almost Sure Safety and Continual Improvement in Reinforcement Learning (opens in a new tab)

  2. Control of multiclass queueing systems with abandonments and adversarial customers

    … priority policies and an effective approximate policy improvement algorithm. We also consider the scenario of a strategic adversary who chooses where to attack. We model the interaction of the server and adversary as a two-person zero-sum game. We develop an effective heuristic based on an …

    lancaster Download PDF for Control of multiclass queueing systems with abandonments and adversarial customers (opens in a new tab)

  3. Βέλτιστες μονότονες πολιτικές σε προβλήματα ελέγχου στοχαστικών διαδικασιών

    Στην παρούσα διατριβή μελετώνται διάφορα προβλήματα βέλτιστου ελέγχου στοχαστικών διαδικασιών τα οποία μπορούν να περιγραφούν με κατάλληλα Μαρκοβιανά ή ημι-Μαρκοβιανά μοντέλα αποφάσεων. Τα προβλήματα σχετίζονται με το βέλτιστο έλεγχο μιας διδιάστατης επιδημικής διαδικασίας, με τη βέλτιστη …

    greece Repository record for Βέλτιστες μονότονες πολιτικές σε προβλήματα ελέγχου στοχαστικών διαδικασιών (opens in a new tab)